File size: 4,866 Bytes
872c781 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
wandb_version: 1
__cached__setup_devices:
desc: null
value: cpu
_n_gpu:
desc: null
value: 0
_wandb:
desc: null
value:
cli_version: 0.10.33
framework: huggingface
huggingface_version: 4.9.0.dev0
is_jupyter_run: false
is_kaggle_kernel: false
python_version: 3.8.10
t:
1:
- 1
- 3
- 11
4: 3.8.10
5: 0.10.33
6: 4.9.0.dev0
8:
- 5
adafactor:
desc: null
value: false
adam_beta1:
desc: null
value: 0.9
adam_beta2:
desc: null
value: 0.98
adam_epsilon:
desc: null
value: 1.0e-08
block_size:
desc: null
value: 512
cache_dir:
desc: null
value: null
config_name:
desc: null
value: /home/cahya/Work/flax-community/gpt2-medium-indonesian
dataloader_drop_last:
desc: null
value: false
dataloader_num_workers:
desc: null
value: 64
dataloader_pin_memory:
desc: null
value: true
dataset_config_name:
desc: null
value: unshuffled_deduplicated_id
dataset_name:
desc: null
value: oscar
ddp_find_unused_parameters:
desc: null
value: null
debug:
desc: null
value: []
deepspeed:
desc: null
value: null
disable_tqdm:
desc: null
value: false
do_eval:
desc: null
value: true
do_predict:
desc: null
value: false
do_train:
desc: null
value: true
dtype:
desc: null
value: float32
eval_accumulation_steps:
desc: null
value: null
eval_steps:
desc: null
value: 10
evaluation_strategy:
desc: null
value: IntervalStrategy.NO
fp16:
desc: null
value: false
fp16_backend:
desc: null
value: auto
fp16_full_eval:
desc: null
value: false
fp16_opt_level:
desc: null
value: O1
gradient_accumulation_steps:
desc: null
value: 1
greater_is_better:
desc: null
value: null
group_by_length:
desc: null
value: false
ignore_data_skip:
desc: null
value: false
label_names:
desc: null
value: null
label_smoothing_factor:
desc: null
value: 0.0
learning_rate:
desc: null
value: 0.0024
length_column_name:
desc: null
value: length
load_best_model_at_end:
desc: null
value: false
local_rank:
desc: null
value: -1
log_level:
desc: null
value: -1
log_level_replica:
desc: null
value: -1
log_on_each_node:
desc: null
value: true
logging_dir:
desc: null
value: /home/cahya/Work/flax-community/gpt2-medium-indonesian/runs/Jul09_14-14-49_t1v-n-528d9406-w-0
logging_first_step:
desc: null
value: false
logging_steps:
desc: null
value: 500
logging_strategy:
desc: null
value: IntervalStrategy.STEPS
lr_scheduler_type:
desc: null
value: SchedulerType.LINEAR
max_eval_samples:
desc: null
value: 1000
max_grad_norm:
desc: null
value: 1.0
max_steps:
desc: null
value: -1
max_train_samples:
desc: null
value: 10000
metric_for_best_model:
desc: null
value: null
model_name_or_path:
desc: null
value: null
model_type:
desc: null
value: gpt2
mp_parameters:
desc: null
value: ''
no_cuda:
desc: null
value: false
num_train_epochs:
desc: null
value: 20.0
output_dir:
desc: null
value: /home/cahya/Work/flax-community/gpt2-medium-indonesian
overwrite_cache:
desc: null
value: false
overwrite_output_dir:
desc: null
value: true
past_index:
desc: null
value: -1
per_device_eval_batch_size:
desc: null
value: 24
per_device_train_batch_size:
desc: null
value: 24
per_gpu_eval_batch_size:
desc: null
value: null
per_gpu_train_batch_size:
desc: null
value: null
prediction_loss_only:
desc: null
value: false
preprocessing_num_workers:
desc: null
value: 64
push_to_hub:
desc: null
value: true
push_to_hub_model_id:
desc: null
value: gpt2-medium-indonesian
push_to_hub_organization:
desc: null
value: null
push_to_hub_token:
desc: null
value: null
remove_unused_columns:
desc: null
value: true
report_to:
desc: null
value:
- tensorboard
- wandb
resume_from_checkpoint:
desc: null
value: null
run_name:
desc: null
value: /home/cahya/Work/flax-community/gpt2-medium-indonesian
save_on_each_node:
desc: null
value: false
save_steps:
desc: null
value: 10
save_strategy:
desc: null
value: IntervalStrategy.STEPS
save_total_limit:
desc: null
value: null
seed:
desc: null
value: 42
sharded_ddp:
desc: null
value: []
skip_memory_metrics:
desc: null
value: true
test_log:
desc: null
value: 12345
tokenizer_name:
desc: null
value: /home/cahya/Work/flax-community/gpt2-medium-indonesian
tpu_metrics_debug:
desc: null
value: false
tpu_num_cores:
desc: null
value: null
train_file:
desc: null
value: null
use_fast_tokenizer:
desc: null
value: true
use_legacy_prediction_loop:
desc: null
value: false
validation_file:
desc: null
value: null
validation_split_percentage:
desc: null
value: 5
warmup_ratio:
desc: null
value: 0.0
warmup_steps:
desc: null
value: 1000
weight_decay:
desc: null
value: 0.01
|